Conversation Engine With Sentiment-Driven Speech for Real-Time Training

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing conversation training methods face limitations due to the scarcity and cost of trainers/actors, and asynchronous feedback, necessitating improved systems for efficient and flexible training.

Innovation Solution

A conversation engine utilizing an input module, sentiment and text feature extractors, and a training generator to provide synchronized feedback through a speech generator, enhancing conversation training with customized and flexible training configurations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If trainers or actors are used for conversation training, then the training quality and realism are improved, but the cost and availability are worsened

Engineering Contradiction:
Improvetraining qualityVSAvoidavailability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent creates a virtual agent that copies and simulates the role of human trainers or actors in conversation training scenarios. The virtual agent replicates realistic conversation interactions without requiring actual human trainers, thereby maintaining training quality while eliminating availability and cost constraints associated with human actors.

Inventive Principle:
Principle #26Copying

2Reliability

If human trainers provide feedback, then the training effectiveness is improved, but the feedback timing becomes asynchronous and delayed

Engineering Contradiction:
Improvetraining effectivenessVSAvoidfeedback delay
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent implements an automated feedback mechanism where the virtual agent provides real-time feedback during conversation training. The system analyzes the trainee's responses and delivers immediate feedback without the asynchronous delays inherent in human trainer interactions, thereby reducing time loss while maintaining training effectiveness.

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If a conversation engine with multiple processing modules is implemented, then the training functionality and analysis capability are improved, but the device complexity increases

Engineering Contradiction:
Improvetraining functionalityVSAvoidsystem structure
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges multiple processing functions (sentiment analysis, text analysis, speech generation, and training configuration) into a single integrated virtual agent system. Rather than separate complex modules, these functions are combined within the virtual agent architecture, providing comprehensive training functionality while managing system complexity through unified design.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP4160591B1Conversation engine and related methods
Publication Date: 2025.10.29 GN HEARING AS
  • EP4160591B1 patent drawingFigure 1
  • EP4160591B1 patent drawingFigure 2
  • EP4160591B1 patent drawingFigure 3

AI summary

A conversation engine is disclosed. The conversation engine comprises an input module for provision of speech data based on a speech signal, including first speech data based on a first speech signal from a first speaker. The conversation engine comprises a sentiment feature extractor for provision of sentiment metric data based on the speech data, the sentiment metric data including first sentiment metric data based on the first speech data. The conversation engine comprises a text feature extractor for provision of text metric data based on the speech data, the text metric data including first text metric data based on the first speech data. The conversation engine comprises a training generator configured to generate a training configuration based on the sentiment metric data and/or the text metric data. The training configuration comprises a first output sentiment and a first output text based on one or more of the first sentiment metric data and the first text metric data. The conversation engine comprises a speech generator configured to output a first output speech signal according to the first output sentiment and the first output text.